1. Joint Modeling
1.1 Trace plots for convergence check
The current MCMC setting is:
- 300000 iteration;
- 200000 burn-in;
- 100 thinning.
1.2 Gelman and Rubin’s convergence check
## Potential scale reduction factors:
##
## Point est. Upper C.I.
## HDevsum 1.00 1.01
## LDevsum 1.00 1.00
## dh0 1.09 1.36
## dh1 1.10 1.36
## dl0 1.05 1.21
## dl1 1.02 1.09
##
## Multivariate psrf
##
## 1.1
1.3 ACF Plots
Here we plotted ACF plots for the following variables:
- Total deviance;
- Variables that didn’t pass the convergence check.
1.4 WAIC results
| LevelH | LevelL | |
|---|---|---|
| DIC | 1211.34549 | 22611.0629 |
| DIC3 | 1155.31617 | 22713.2479 |
| PWAIC | 41.91592 | 255.0105 |
| WAIC | 1181.63383 | 22735.5758 |
2. Separate Modeling of High-Level
2.1 Trace plots for convergence check
The current MCMC setting is:
- 300000 iteration;
- 200000 burn-in;
- 100 thinning.
2.2 Gelman and Rubin’s convergence check
## Potential scale reduction factors:
##
## Point est. Upper C.I.
## HDevsum 1.00 1.00
## LDevsum 1.00 1.02
## dh0 1.25 1.84
## dh1 1.24 1.80
## dl0 1.01 1.01
## dl1 1.01 1.02
##
## Multivariate psrf
##
## 1.15
2.3 ACF Plots
Here we plotted ACF plots for the following variables:
- Total deviance;
- Variables that didn’t pass the convergence check.
2.4 WAIC results
| H0a | |
|---|---|
| DIC | 1212.78403 |
| DIC3 | 1155.46726 |
| PWAIC | 41.76234 |
| WAIC | 1181.55251 |
3. Separate Modeling for Low-level
3.1 Trace plots for convergence check
The current MCMC setting is:
- 300000 iteration;
- 200000 burn-in;
- 100 thinning.
3.2 Gelman and Rubin’s convergence check
## Potential scale reduction factors:
##
## Point est. Upper C.I.
## Devsum 1.00 1.01
## LDevsum 1.00 1.02
## dl0 1.01 1.01
## dl1 1.01 1.02
##
## Multivariate psrf
##
## 1.01
3.3 ACF Plots
Here we plotted ACF plots for the following variables:
- Total deviance;
- Variables that didn’t pass the convergence check.
3.4 WAIC results
| L1 | |
|---|---|
| DIC | 22610.7042 |
| DIC3 | 22714.5827 |
| PWAIC | 256.2921 |
| WAIC | 22737.2187 |